[Misc] Upgrade vllm hash to 12_14 (#5000)

### What this PR does / why we need it?

### Does this PR introduce _any_ user-facing change?
1. fix https://github.com/vllm-project/vllm/pull/27938
2. fix https://github.com/vllm-project/vllm/pull/27145
pooling models now supports chunked prefill and prefix caching,
3. fix https://github.com/vllm-project/vllm/pull/30181
define the CPU fields in the field config where they really belong.
4. fix https://github.com/vllm-project/vllm/pull/28168
define the CPU fields in the field config where they really belong.
5. fix https://github.com/vllm-project/vllm/pull/30201
some moudle rename
6. fix https://github.com/vllm-project/vllm/pull/29067
fusedmoe moudle refactor
7. fix https://github.com/vllm-project/vllm/pull/29066
fusedmoe moudle refactor
8. fix https://github.com/vllm-project/vllm/pull/29624
### How was this patch tested?

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: wangli <wangli858794774@gmail.com>

vllm_ascend/attention/mla_v1.py

@@ -41,7 +41,7 @@ from vllm_ascend.quantization.w8a8 import AscendW8A8LinearMethod
 from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_ND, ACL_FORMAT_FRACTAL_NZ,
                                flashcomm2_o_shared_enabled, is_enable_nz,
                                weak_ref_tensors)
-from vllm_ascend.worker.npu_input_batch import InputBatch
+from vllm_ascend.worker.npu_input_batch import NPUInputBatch
 
 if TYPE_CHECKING:
     from vllm.v1.core.sched.output import SchedulerOutput
@@ -280,7 +280,7 @@ class AscendMLAMetadataBuilder:
                                               dtype=torch.uint8,
                                               device=device)
 
-    def reorder_batch(self, input_batch: "InputBatch",
+    def reorder_batch(self, input_batch: "NPUInputBatch",
                       scheduler_output: "SchedulerOutput") -> bool:
         # We now want to reorder the batch so that the "decode" requests are at
         # the front and the "prefill" requests are at the using the least amount